agent-tdd-london-swarm

Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

1.01x

Quality

Does it follow best practices?

Impact

93%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-tdd-london-swarm/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an extremely weak description that fails on every dimension. It provides only an invocation command and a cryptic name ('tdd-london-swarm') without explaining what the skill does, when to use it, or what domain it operates in. It is essentially unusable for skill selection purposes.

Suggestions

Add a clear 'what' clause describing concrete actions, e.g., 'Guides test-driven development using the London school (mockist) approach, creating tests with mocks/stubs before implementation, working outside-in from acceptance tests to unit tests.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about TDD, London school testing, mockist TDD, outside-in development, or writing tests with mocks and stubs.'

Include natural keywords users would actually say, such as 'test-driven development', 'TDD', 'mocking', 'outside-in testing', 'red-green-refactor', and 'London school'.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It only states it's an 'agent skill' and how to invoke it, with no indication of what it actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command, not functional information or trigger guidance.	1 / 3
Trigger Term Quality	The only potentially meaningful terms are 'tdd-london-swarm' which is a technical/internal identifier, not natural language a user would use. No natural keywords like 'test-driven development', 'London school TDD', 'testing', or 'red-green-refactor' are present.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no basis for distinguishing this skill from any other agent skill. Without knowing what it does, there's no way to avoid conflicts.	1 / 3
	Total	4 / 12 Passed

Implementation

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a verbose, conceptual document that explains London School TDD philosophy rather than providing actionable instructions for an agent. The code examples use fictional APIs (swarmCoordinator, SwarmContractMonitor, createSwarmMock) that aren't real libraries or provided implementations, making them non-executable. The content reads more like a blog post about mockist TDD than a practical skill file that would help Claude perform specific tasks.

Suggestions

Replace fictional API examples (swarmCoordinator, SwarmContractMonitor) with real, executable code using actual testing libraries (Jest, Vitest) or provide the actual implementations in bundle files.

Add a concrete step-by-step workflow: 1) Write failing acceptance test, 2) Define mocks for collaborators, 3) Implement to pass, 4) Verify mock interactions, 5) Run full suite — with explicit validation at each step.

Cut the content by at least 60% — remove the 'Core Responsibilities' list, the 'Best Practices' section (Claude knows these), and deduplicate the many similar mock verification examples into one clear, complete example.

Define what 'swarm coordination' actually means in concrete terms — what files to read/write, what commands to run, what other agents exist — or remove the swarm references entirely if no real coordination mechanism exists.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~200+ lines. Explains basic TDD concepts Claude already knows (what outside-in TDD is, what mocks are, what behavior verification means). The 'Core Responsibilities' section is pure padding. Many code examples are repetitive and illustrate the same concept (mock setup, verification) multiple times. The 'swarm coordination' concept is vaguely defined with pseudo-APIs (swarmCoordinator, SwarmContractMonitor) that don't correspond to real tools.	1 / 3
Actionability	Despite having many code blocks, none are truly executable or copy-paste ready. Functions like `createSwarmMock`, `extendSwarmMock`, `SwarmContractMonitor`, `swarmCoordinator.notifyTestStart` are fictional APIs with no implementation or library reference. The code examples are essentially pseudocode dressed up as TypeScript. There are no concrete commands, no real tool invocations, and no specific instructions for what Claude should actually do when invoked.	1 / 3
Workflow Clarity	No clear step-by-step workflow for how the agent should operate when given a task. The numbered sections (1, 2, 3) under each heading are conceptual categories, not sequential steps. There are no validation checkpoints, no error handling guidance, and no feedback loops for the actual TDD process (red-green-refactor cycle is never explicitly sequenced). The 'Feedback Loops' section is a bullet list of abstract aspirations, not actionable workflow steps.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files and no bundle files to support it. All content is inline with no clear hierarchy or navigation. The document could easily be split into methodology, swarm coordination, and examples, but instead everything is dumped into one long file with repetitive sections.	1 / 3
	Total	4 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 9d4a9ea

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.